1.Structured prediction methods are essentially a combination of classification and graphical modeling.

2.They combine the ability of graphical models to compactly model multivariate data with the ability of classification methods to perform prediction using large sets of input features.

3.The input x is divided into feature vectors {x0,x1, . . . ,xT }. Each xs contains various information about the word at position s, such as its identity, orthographic features such as prefixes and suffixes, membership in domain-specific lexicons, and information in semantic databases such as WordNet.

4.CRFs are essentially a way of combining the advantages of discriminative classification and graphical modeling, combining the ability to compactly model multivariate outputs y with the ability to leverage a large number of input features x for prediction.

5.The difference between generative models and CRFs is thus exactly analogous to the difference between the naive Bayes and logistic regression classifiers. Indeed, the multinomial logistic regression model can be seen as the simplest kind of CRF, in which there is only one output variable.

6.The insight of the graphical modeling perspective is that a distribution over very many variables can often be represented as a product of local functions that each depend on a much smaller subset of variables. This factorization turns out to have a close connection to certain conditional independence relationships among the variables — both types of information being easily summarized by a graph. Indeed, this relationship between factorization, conditional independence, and graph structure comprises much of the power of the graphical modeling framework: the conditional independence viewpoint is most useful for designing models, and the factorization viewpoint is most useful for designing inference algorithms.

7.The principal advantage of discriminative modeling is that it is better suited to including rich, overlapping features.

8.In principle, it may not be clear why these approaches should be so different, because we can always convert between the two methods using Bayes rule. For example, in the naive Bayes model, it is easy to convert the joint p(y)p(x|y) into a conditional distribution p(y|x). Indeed, this conditional has the same form as the logistic regression model (2.9). And if we managed to obtain a “true” generative model for the data, that is, a distribution p∗(y,x) = p∗(y)p∗(x|y) from which the data were actually sampled, then we could simply compute the true p∗(y|x), which is exactly the target of the discriminative approach. But it is precisely because we never have the true distribution that the two approaches are different in practice. Estimating p(y)p(x|y) first, and then computing the resulting p(y|x) (the generative approach)yields a different estimate than estimating p(y|x) directly. In other words, generative and discriminative models both have the aim of stimating p(y|x), but they get there in different ways.

an introduction to conditional random fields的更多相关文章

  1. (转)Image Segmentation with Tensorflow using CNNs and Conditional Random Fields

    Daniil's blog Machine Learning and Computer Vision artisan. About/ Blog/ Image Segmentation with Ten ...

  2. 论文翻译:Conditional Random Fields as Recurrent Neural Networks

    Conditional Random Fields as Recurrent Neural Networks ICCV2015    cite237 1摘要: 像素级标注的重要性(语义分割 图像理解) ...

  3. Conditional Random Fields (CRF) 初理解

    1,Conditional Random Fields

  4. 条件随机场 Conditional Random Fields

    简介 假设你有冠西哥一天生活中的照片(这些照片是按时间排好序的),然后你很无聊的想给每张照片打标签(Tag),比如这张是冠西哥在吃饭,那张是冠西哥在睡觉,那么你该怎么做呢? 一种方法是不管这些照片的序 ...

  5. NLP —— 图模型(二)条件随机场(Conditional random field,CRF)

    本文简单整理了以下内容: (一)马尔可夫随机场(Markov random field,无向图模型)简单回顾 (二)条件随机场(Conditional random field,CRF) 这篇写的非常 ...

  6. 条件随机场(conditional random field,CRF)模型初探

    0. 引言 0x1:为什么会有条件随机场?它解决了什么问题? 在开始学习CRF条件随机场之前,我们需要先了解一下这个算法的来龙去脉,它是在什么情况下被提出的,是从哪个算法演进而来的,它又解决了哪些问题 ...

  7. 条件随机场conditional random field

    主要翻译自http://blog.echen.me/2012/01/03/introduction-to-conditional-random-fields/,原作者是MIT的大神,加入了一些我自己的 ...

  8. 条件随机场Conditional Random Field-CRF入门级理解

    条件随机场Conditional Random Field-CRF入门级理解   有向图与无向图模型 CRF模型是一个无向概率图模型,更宽泛地说,它是一个概率图模型.现实世界的一些问题可以用概率图模型 ...

  9. 马尔可夫随机场(Markov random fields) 概率无向图模型 马尔科夫网(Markov network)

    上面两篇博客,解释了概率有向图(贝叶斯网),和用其解释条件独立.本篇将研究马尔可夫随机场(Markov random fields),也叫无向图模型,或称为马尔科夫网(Markov network) ...

随机推荐

  1. [JS] HTML QQ分享界面js代码

    @ - @ :可以自己指定分享内容等....内含JS脚本 <html> <head> <title></title> <script type=& ...

  2. ajaxSubmit与ajaxFileUpload的空值

    ajaxSubmit发现正文无内容, ajaxFileUpload发现无上传内容, 嗯,你只是忘记了 html 中控件的 name 没有指定,这哥们不认 id 的.

  3. Windows 8.1 开发过程中遇到的小问题

    最近在开发Windows 8 应用的时候碰到了一个莫名的问题,错误内容如下:(其中 **.DLL是本地创建的项目,在主项目中添加了引用,其中大部分代码是MVVM light 框架库的代码) Syste ...

  4. 安装 Dubbo 管理控制台

    Dubbo管控台可以对注册到 zookeeper 注册中心的服务或服务消费者进行管理,但管控台是否正常对Dubbo服务没有影响,管控台也不需要高可用,因此可以单节点部署. IP: 192.168.1. ...

  5. PHP读取日志里数据方法理解

    需要函数: fopen($file, "r")打开文件 fgets($file, 1024 * 10)读取一行,注意设置字节数大小,默认的1024B可能太小了 strpos($lo ...

  6. iOS开发——高级技术&地图功能的实现

    地图功能的实现 因为有个项目要在地图中显示位置,所以用到了MapKit. 记录下来,以免以后忘记. 加入MapKit library 首先得在项目中加入MapKit,如图 MapView 先增加一个V ...

  7. java防止脚本注入,通过拦截器实现

    1:利用action过滤 package com.tsou.comm.servlet; import java.util.Enumeration; import java.util.Map; impo ...

  8. python数据持久存储:pickle模块的使用

    python的pickle模块实现了基本的数据序列和反序列化.通过pickle模块的序列化操作我们能够将程序中运行的对象信息保存到文件中去,永久存储:通过pickle模块的反序列化操作,我们能够从文件 ...

  9. Ruby on Rails框架开发学习

    学习地址:http://www.ixueyun.com/lessons/detail-lessonId-685.html 一.课程概述 软件开发在经历了面向过程编程的阶段,现在正大行其道的是敏捷开发, ...

  10. DataGridView很详细的用法(转载)

    一.DataGridView 取得或者修改当前单元格的内容: 当前单元格指的是 DataGridView 焦点所在的单元格,它可以通过 DataGridView 对象的 CurrentCell 属性取 ...